import copy
import pdb
from typing import Optional

import torch
import torch.nn.functional as F
from torch import nn, Tensor

def mask_logits(inputs, mask, mask_value=-1e30):
    mask = mask.type(torch.float32)
    return inputs + (1.0 - mask) * mask_value


class Transformer(nn.Module):

    def __init__(self, d_model=512, nhead=8, num_encoder_layers=4,
                 num_decoder_layers=6, dim_feedforward=2048, dropout=0.1,
                 activation="relu", normalize_before=False,  # False as default
                 return_intermediate_dec=False):
        super().__init__()

        encoder_layer = TransformerEncoderLayer(d_model, nhead, dim_feedforward,
                                                dropout, activation, normalize_before)
        encoder_norm = nn.LayerNorm(d_model) if normalize_before else None
        self.encoder = TransformerEncoder(encoder_layer, num_encoder_layers, encoder_norm)

        self._reset_parameters()

        self.d_model = d_model
        self.nhead = nhead

    def _reset_parameters(self):
        for p in self.parameters():
            if p.dim() > 1:
                nn.init.xavier_uniform_(p)

    def forward(self, src, mask, pos_embed):
        """
        Args:
            src: (batch_size, L, d)
            mask: (batch_size, L)
            query_embed: (#queries, d) -> my imple (batch_size, d) and #queries=1
            pos_embed: (batch_size, L, d) the same as src

        Returns:

        """
        # flatten NxCxHxW to HWxNxC
        src = src.permute(1, 0, 2)  # (L, batch_size, d)
        pos_embed = pos_embed.permute(1, 0, 2)   # (L, batch_size, d)

        memory = self.encoder(src, src_key_padding_mask=mask, pos=pos_embed)
        memory = memory.transpose(0, 1)

        return memory


class TransformerEncoder(nn.Module):
    def __init__(self, encoder_layer, num_layers, norm=None, return_intermediate=False):
        super().__init__()
        self.layers = _get_clones(encoder_layer, num_layers)
        self.num_layers = num_layers
        self.norm = norm
        self.return_intermediate = return_intermediate

    def forward(self, src,
                mask: Optional[Tensor] = None,
                src_key_padding_mask: Optional[Tensor] = None,
                pos: Optional[Tensor] = None):
        output = src

        intermediate = []

        for layer in self.layers:
            output = layer(output, src_mask=mask,
                           src_key_padding_mask=src_key_padding_mask, pos=pos)
            if self.return_intermediate:
                intermediate.append(output)

        if self.norm is not None:
            output = self.norm(output)

        if self.return_intermediate:
            return torch.stack(intermediate)

        return output


class TransformerEncoderLayer(nn.Module):

    def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1,
                 activation="relu", normalize_before=False):
        super().__init__()
        self.self_attn = nn.MultiheadAttention(d_model, nhead, dropout=dropout)
        # Implementation of Feedforward model
        self.linear1 = nn.Linear(d_model, dim_feedforward)
        self.dropout = nn.Dropout(dropout)
        self.linear2 = nn.Linear(dim_feedforward, d_model)

        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.dropout1 = nn.Dropout(dropout)
        self.dropout2 = nn.Dropout(dropout)

        self.activation = _get_activation_fn(activation)
        self.normalize_before = normalize_before

    def with_pos_embed(self, tensor, pos: Optional[Tensor]):
        return tensor if pos is None else tensor + pos

    def forward_post(self,
                     src,
                     src_mask: Optional[Tensor] = None,
                     src_key_padding_mask: Optional[Tensor] = None,
                     pos: Optional[Tensor] = None):
        q = k = self.with_pos_embed(src, pos)
        src2 = self.self_attn(q, k, value=src, attn_mask=src_mask,
                              key_padding_mask=src_key_padding_mask)[0]
        src = src + self.dropout1(src2)
        src = self.norm1(src)
        src2 = self.linear2(self.dropout(self.activation(self.linear1(src))))
        src = src + self.dropout2(src2)
        src = self.norm2(src)
        return src

    def forward(self, src,
                src_mask: Optional[Tensor] = None,
                src_key_padding_mask: Optional[Tensor] = None,
                pos: Optional[Tensor] = None):
        if self.normalize_before:
            return self.forward_pre(src, src_mask, src_key_padding_mask, pos)
        return self.forward_post(src, src_mask, src_key_padding_mask, pos)


def _get_clones(module, N):
    return nn.ModuleList([copy.deepcopy(module) for i in range(N)])


def build_transformer(args):
    return Transformer(
        d_model=args.hidden_dim,
        dropout=args.dropout,
        nhead=args.nheads,
        dim_feedforward=args.dim_feedforward,
        num_encoder_layers=args.enc_layers,
        num_decoder_layers=args.dec_layers,
        normalize_before=args.pre_norm,
        return_intermediate_dec=True,
    )

def _get_activation_fn(activation):
    """Return an activation function given a string"""
    if activation == "relu":
        return F.relu
    if activation == "gelu":
        return F.gelu
    if activation == "glu":
        return F.glu
    raise RuntimeError(F"activation should be relu/gelu, not {activation}.")